Retail Fraud is on the rise and affecting all of us, disputed charges on credit cards and billions of dollars in lost revenue have caused a rapid increase in product prices. The retail edition of the LexisNexis® Risk Solutions True Cost of FraudTM Study found the cost of fraud to merchants across the U.S. increased 7.3% over the last year. These fraudulent use cases are becoming more sophisticated and include: lay-away fraud, credit card fraud, buy now pay later, cascaded transactions, return & loyalty fraud, synthetic or stolen ID, financial crimes, insider threat, and compliance & audit.
In addition, and seemingly unrelated, retail fraud is becoming a conduit for rings of thieves that can attack via transactions or credit cards used for legitimate goods and services. The rise in retail fraud and our current supply chain issues have increased the need for real-time analytics and real-time ‘prevent and intervene’ strategies.
The focus of this webinar is to identify how Machine Learning, Visualizations and new technology like Graph can directly increase the accuracy and output of systems. We will also discuss how including the ‘Human in the Loop’ can get you ahead in your fraud detection strategies. This event is designed as a 'Speed Dating' format, focusing on key topics for under 15 minutes in order to maximize the insights. During this online meetup, you'll learn from our experts on how Expero and TigerGraph can unlock the potential in your organization. We will feature unique Expero lightning talks on ML & Business Visualization technology, followed by a short Q&A session.
Key Challenges in Retail Fraud - Discuss the top challenges in retail fraud - lay-away fraud, credit card fraud, buy now pay later, cascaded transactions, return & loyalty fraud, synthetic or stolen ID, financial crimes, insider threat, and compliance & audit - and technology solutions for detection and prevention
Technology that will reduce false positives by 20+% - Review ML & Graph algorithm combination techniques with Graph and other platforms to reduce false positive signals
Fraud based Data Products for Preventive & Predictive analytics - How different teams and roles in an organization - fraud managers, investigators, risk, compliance, etc. - can utilize data products to prevent and predict fraud within their retail organization
Using Visualizations for Explainable Machine Learning - Show practical uses and methods for fraud identification, complex dependency and case management